AI-big data analytics for building automation and management systems: a survey, actual challenges and future perspectives

Artificial Intelligence Review, Год журнала: 2022, Номер 56(6), С. 4929 - 5021

Опубликована: Окт. 15, 2022

In theory, building automation and management systems (BAMSs) can provide all the components functionalities required for analyzing operating buildings. However, in reality, these only ensure control of heating ventilation air conditioning system systems. Therefore, many other tasks are left to operator, e.g. evaluating buildings' performance, detecting abnormal energy consumption, identifying changes needed improve efficiency, ensuring security privacy end-users, etc. To that end, there has been a movement developing artificial intelligence (AI) big data analytic tools as they offer various new tailor-made solutions incredibly appropriate practical management. Typically, help operator (i) tons connected equipment data; and; (ii) making intelligent, efficient, on-time decisions performance. This paper presents comprehensive systematic survey on using AI-big analytics BAMSs. It covers AI-based tasks, load forecasting, water management, indoor environmental quality monitoring, occupancy detection, The first part this adopts well-designed taxonomy overview existing frameworks. A review is conducted about different aspects, including learning process, environment, computing platforms, application scenario. Moving on, critical discussion performed identify current challenges. second aims at providing reader with insights into real-world analytics. Thus, three case studies demonstrate use BAMSs presented, focusing anomaly detection residential office buildings performance optimization sports facilities. Lastly, future directions valuable recommendations identified reliability intelligent

Язык: Английский

---

A comparative study of deep learning and Internet of Things for precision agriculture

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 122, С. 106034 - 106034

Опубликована: Март 6, 2023

Язык: Английский

---

Deep learning: systematic review, models, challenges, and research directions

Neural Computing and Applications, Год журнала: 2023, Номер 35(31), С. 23103 - 23124

Опубликована: Сен. 7, 2023

Abstract The current development in deep learning is witnessing an exponential transition into automation applications. This can provide a promising framework for higher performance and lower complexity. ongoing undergoes several rapid changes, resulting the processing of data by studies, while it may lead to time-consuming costly models. Thus, address these challenges, studies have been conducted investigate techniques; however, they mostly focused on specific approaches, such as supervised learning. In addition, did not comprehensively other techniques, unsupervised reinforcement techniques. Moreover, majority neglect discuss some main methodologies learning, transfer federated online Therefore, motivated limitations existing this study summarizes techniques supervised, unsupervised, reinforcement, hybrid learning-based addition each category, brief description categories their models provided. Some critical topics namely, transfer, federated, models, are explored discussed detail. Finally, challenges future directions outlined wider outlooks researchers.

Язык: Английский

---

An innovative deep anomaly detection of building energy consumption using energy time-series images

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 119, С. 105775 - 105775

Опубликована: Янв. 6, 2023

Язык: Английский

---

Video surveillance using deep transfer learning and deep domain adaptation: Towards better generalization

Engineering Applications of Artificial Intelligence, Год журнала: 2022, Номер 119, С. 105698 - 105698

Опубликована: Дек. 16, 2022

Recently, developing automated video surveillance systems (VSSs) has become crucial to ensure the security and safety of population, especially during events involving large crowds, such as sporting events. While artificial intelligence (AI) smooths path computers think like humans, machine learning (ML) deep (DL) pave way more, even by adding training components. DL algorithms require data labeling high-performance effectively analyze understand recorded from fixed or mobile cameras installed in indoor outdoor environments. However, they might not perform expected, take much time training, have enough input generalize well. To that end, transfer (DTL) domain adaptation (DDA) recently been proposed promising solutions alleviate these issues. Typically, can (i) ease process, (ii) improve generalizability ML models, (iii) overcome scarcity problems transferring knowledge one another task another. Although increasing number articles develop DTL- DDA-based VSSs, a thorough review summarizes criticizes state-of-the-art is still missing. this paper introduces, best authors' knowledge, first overview existing shed light on their benefits, discuss challenges, highlight future perspectives.

Язык: Английский

---

Deep transfer learning for automatic speech recognition: Towards better generalization

Knowledge-Based Systems, Год журнала: 2023, Номер 277, С. 110851 - 110851

Опубликована: Июль 29, 2023

Язык: Английский

---

A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions

IEEE Access, Год журнала: 2024, Номер 12, С. 3768 - 3789

Опубликована: Янв. 1, 2024

Automating the monitoring of industrial processes has potential to enhance efficiency and optimize quality by promptly detecting abnormal events thus facilitating timely interventions. Deep learning, with its capacity discern non-trivial patterns within large datasets, plays a pivotal role in this process. Standard deep learning methods are suitable solve specific task given type data. During training, demands volumes labeled However, due dynamic nature environment, it is impractical acquire large-scale data for standard training every slightly different case anew. transfer offers solution problem. By leveraging knowledge from related tasks accounting variations distributions, framework solves new little or even no additional The approach bypasses need retrain model scratch setup dramatically reduces requirement. This survey first provides an in-depth review examining problem settings classifying prevailing methods. Moreover, we delve into applications context broad spectrum time series anomaly detection prevalent primary domains, e.g., manufacturing process monitoring, predictive maintenance, energy management, infrastructure facility monitoring. We discuss challenges limitations contexts conclude practical directions actionable suggestions address leverage diverse increasingly production environment.

Язык: Английский

---

From time-series to 2D images for building occupancy prediction using deep transfer learning

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 119, С. 105786 - 105786

Опубликована: Янв. 12, 2023

Building occupancy information could aid energy preservation while simultaneously maintaining the end-user comfort level. Energy conservation becomes essential since resources are scarce and human dependency on appliances is only exponentially increasing. While intrusive sensors (i.e., cameras microphones) can raise privacy concerns, this paper presents an innovative non-intrusive detection approach using environmental sensor data (e.g., temperature, humidity, carbon dioxide (CO2), light sensors). The proposed scheme transforms multivariate time-series into images for better encoding extracting relevant features. utilized image transformation method based normalization matrix conversion. Precisely, by representing in 2D space, kernel move two directions it one direction when applied to a 1D signal. Moreover, machine learning (ML) deep (DL) techniques classify patterns. Several simulations used evaluate approach; mainly, we investigated pre-trained custom convolutional neural network (CNN) models. latter attained accuracy of 99.00%. Additionally, pixel extracted from generated subjected traditional ML methods. Throughout numerous comparison settings, was observed that strategy provided optimal balance 99.42% performance minimal training time across datasets.

Язык: Английский

---

Revolutionizing generative pre-traineds: Insights and challenges in deploying ChatGPT and generative chatbots for FAQs

Expert Systems with Applications, Год журнала: 2024, Номер 246, С. 123224 - 123224

Опубликована: Янв. 19, 2024

Язык: Английский

---

A systematic review and comprehensive analysis of building occupancy prediction

Renewable and Sustainable Energy Reviews, Год журнала: 2024, Номер 193, С. 114284 - 114284

Опубликована: Янв. 16, 2024

Язык: Английский

---